spec_score

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses key behaviors: the tool normalizes scores, calculates balance, and returns a verdict, and it explains the meaning of each axis. However, it fails to describe the exact format or structure of the return value (e.g., whether the verdict is a string, object, or includes the normalized scores), which is a notable gap given the absence of an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with an initial purpose statement followed by bullet-point explanations of the axes. Every sentence contributes value: it defines the axes, explains the process (normalization, balance, verdict), and conveys the practical importance (balanced specs reduce hallucinations). There is no redundancy or unnecessary filler, making it both concise and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description thoroughly covers the tool's purpose, parameters, and internal logic, which is quite complete for a tool with 7 parameters and full schema coverage. However, it does not specify the return value's format or structure, and since there is no output schema, this absence leaves a noticeable gap in understanding what the tool actually produces. Sibling tools are not referenced, but that is minor compared to the missing output details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the input schema already describes each parameter (e.g., 'Completeness score 0.0-1.0'), the tool description adds substantial meaning by defining what each axis actually measures: completeness ('Can an LLM understand the full scope?'), clarity ('Is it unambiguous?'), constraints ('Are boundaries defined?'), and specificity ('Concrete testable details?'). It also clarifies the purpose of 'weakest' and 'tip' by stating that the weakest axis is the biggest hallucination risk and the tip should improve it. This goes well beyond the schema's basic descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Score a spec/requirement on 4 axes.' It specifies the resource (spec/requirement), the action (score), and details the four axes (completeness, clarity, constraints, specificity). This distinguishes it from siblings like spec_compare and spec_visualize, which focus on comparison and visualization rather than scoring.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool: whenever a spec/requirement needs to be evaluated on four defined axes. It does not explicitly mention alternatives or exclusions, but the purpose is so specific that it naturally separates from comparing or visualizing specs. The statement 'YOU (the LLM) read the spec and score it' indicates the intended workflow, giving a clear usage scenario.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.